The Challenge

  • The planning process in the AirC2 domain is complex and time-consuming
  • A study had to be carried out to determine how AI can support humans in creating a variety of alternative plans more quickly

The Approach

  • Use of DRL algorithms based on the OpenAI implementation
  • Development of an interface to the simulation software
  • Training of AI agents using different reward functions

Result & Added Value

  • Development of an individual OpenAI-Gym Environment
  • Training of AI agents by reinforcement learning within a simulation software provided by the client
  • AI agents with adaptive risk profile
Dr. Marc Großerüschkamp
Head of Software & Data Technologies
We are here to help

Connect with us

Need support in developing your technology solutions? Let’s have a conversation about your projects and explore how we can create value together.